Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

ce-riffrec-feedback-analysis — Claude Code skill: analyze video

Turns recorded product feedback into structured bugs and requirements. Takes video, screenshots or notes from Riffrec and outputs a ready-to-use report for downstream agents.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add EveryInc/compound-engineering-plugin --skill ce-riffrec-feedback-analysis -a claude-code
Open on GitHub

What ce-riffrec-feedback-analysis does

This skill works with recordings captured by Riffrec — a tool that records synchronized screen, voice and event logs in a single session. Input is a zip archive of that data. Output is structured bugs or requirements tied to specific video frames.

The skill picks its analysis depth automatically. A short recording (under ~60 seconds) or simple issue becomes a quick bug report. Longer sessions, multiple problems or feature requests get full analysis with material for brainstorming, then hand off to the ce-brainstorm agent. If input data is incomplete or the analyzer fails, you get a concrete blocker, not a partial result.

Raw video, frames and logs stay local by default. Text artifacts (reports, analyses) go into git only with your consent and if they contain no sensitive data.

What it helps with

  • extract bugs from video recordings with synchronized screen and voice
  • turn unstructured feedback into development requirements
  • set up Riffrec and start recording user feedback sessions
  • combine video, screenshots and event logs into one report
  • prepare material for team discussion of issues

Example prompts for the agent

  • Analyze this Riffrec recording and give me the bugs
  • This is a longer session with several issues. Do a full analysis and hand off to ce-brainstorm
  • Help me set up Riffrec and start recording feedback sessions

How to install ce-riffrec-feedback-analysis

1Skills CLI (Vercel)

npx skills add EveryInc/compound-engineering-plugin --skill ce-riffrec-feedback-analysis -a claude-code

2Manually: put the files in place

~/.claude/skills/ce-riffrec-feedback-analysis/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ce-riffrec-feedback-analysis/

From the same set21

The whole set →
ce-brainstorm EveryInc Turns vague ideas into a structured requirements plan through dialogue. Separates product decisions from code. Claude Code CX Codex Cursor +1 3,900installs ce-compound EveryInc A skill that captures non-obvious reasoning from solved problems as durable project knowledge. Use it when the final code works but the logic behind it might vanish when the next person reads the code. Claude Code CX Codex Cursor +1 3,700installs ce-plan EveryInc Builds structured technical implementation plans without touching production code. Useful when scoping features before passing work to execution agents. Claude Code CX Codex Cursor +1 3,700installs ce-code-review EveryInc Reviews a named diff or pull request for bugs, regressions, tests, and project standards. Use it for a current branch review or a specific PR. Claude Code CX Codex Cursor +1 3,700installs ce-work EveryInc Executes a plan document or build spec end-to-end with local verification. Ideal for implementing features without reopening architectural debates. Claude Code CX Codex Cursor +1 3,600installs ce-doc-review EveryInc This skill reviews requirements, plans, and specs through role-based reviewers. Use it to catch consequential issues in an existing document and apply fixes within the granted authority. Claude Code CX Codex Cursor +1 3,600installs ce-debug EveryInc Finds the root cause of a bug from trigger to symptom and applies a test-first fix. Useful when investigating broken behavior or failing CI logs. Claude Code CX Codex Cursor +1 3,500installs lfg EveryInc Takes a request from intake to a finished result and opens a pull request for code changes. Use it when the user explicitly wants autonomous end-to-end work. Claude Code CX Codex Cursor +1 3,500installs

Similar

printing-press-score mvanhorn Scores a generated CLI against the Steinberger bar and compares two CLIs. Use it when checking output from cli-printing-press. Claude Code CX Codex Cursor +1 6,400installs printing-press-output-review mvanhorn An internal reviewer skill for printed CLIs. It catches plausibility bugs in command output that rule-based checks and live verification miss. Claude Code CX Codex Cursor +1 6,400installs python-debugpy openclaw Guides interactive Python debugging with pdb and debugpy remote attach. Useful for tracking down broken tests, state mutations, and headless processes. Claude Code CX Codex Cursor +1 332installs requesting-code-review Hermes Agent (adapted from obra/superpowers + MorAlekss) Pre-commit code verification pipeline that scans for security flaws, checks test regressions against a baseline, and runs an auto-fixing reviewer subagent. Claude Code CX Codex Cursor +1 467installs ios-simulator callstack Launch, inspect, and debug native, React Native, Expo, and Flutter apps on iOS Simulator from your agent. The agent can tap, type, scroll, validate code changes, and collect error logs. Claude Code CX Codex Cursor +1 5,100installs qa garrytan Automate bug hunting in browser, API, CLI, jobs, workers, and webhooks. Searches code, runs commands, checks logs, and asks clarifying questions. Claude Code CX Codex Cursor +1 457installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. Claude Code CX Codex Cursor +1 673,100installs

Questions about ce-riffrec-feedback-analysis

How do I install ce-riffrec-feedback-analysis in Claude Code?

Run npx skills add EveryInc/compound-engineering-plugin --skill ce-riffrec-feedback-analysis -a claude-code. The skill will be available at ~/.claude/skills/ce-riffrec-feedback-analysis/SKILL.md.

What does ce-riffrec-feedback-analysis do?

It takes recordings from Riffrec (synchronized screen, voice and event capture) and converts them into structured bugs or requirements. Short recordings get quick analysis; longer ones get full analysis with material for further discussion.

Do I need Riffrec to use this skill?

Riffrec is only needed to record sessions. If you don't have it, the skill can help you set it up. If you already have video or screenshots from another source, the skill can analyze those too.

Source text

SKILL.md · MIT 
---
name: ce-riffrec-feedback-analysis
description: "Analyze recorded product feedback into evidence for bugs and requirements. Use when a Riffrec capture or other screen, voice, or notes artifact needs interpretation. Use for Riffrec setup, capture, or sharing help when no recording exists yet."
---

# Riffrec Feedback Analysis

Turn raw product feedback into structured evidence for downstream agents. This skill is the consumption side of [Riffrec](https://github.com/kieranklaassen/riffrec), a capture tool that records synchronized screen + voice + event sessions and emits a `riffrec-*.zip` bundle.

**Done:**

- Setup ends with a current capture/share path.
- Quick analysis ends with one evidence-backed bug report and no durable artifact unless requested.
- Extensive analysis ends with the complete evidence set and a `ce-brainstorm` handoff unless the user asked for extraction only.
- A missing input, analyzer failure, or unresolved route ends with an actionable blocker rather than a partial success claim.

## Choose the path

Route from the input. Read only the references named for that route; do not load the other path references.

- **Setup** — user has no recording yet and asks how to install Riffrec, capture a session, or share feedback. Read `references/install-riffrec.md`.
- **Quick bug report** — input is a short recording (under ~60 seconds), the user describes a single specific issue, or asks for "quick", "small", or "just transcribe". Read `references/analyzer.md`, then `references/quick-bug-report.md`.
- **Extensive analysis** — input is longer, contains multiple issues, requirements, or a workflow walkthrough, or the user wants requirements material. Read `references/analyzer.md`, then `references/extensive-analysis.md`. Continue into `ce-brainstorm` unless the user explicitly asked only to extract or analyze artifacts.

When the input is ambiguous (e.g., a zip arrived without context), inspect the recording length and event count before choosing. If still unclear, ask the user which path applies before running anything heavy.

## Common rules

- Keep raw recordings, audio chunks, zip contents, session dumps, and extracted screenshots local-only by default. Do not commit `raw/` or `frames/` directories unless the user explicitly asks and privacy is acceptable.
- Text/metadata artifacts (requirements kickoff material, analysis summaries, problem analyses, source manifests) may be committed when they are needed for traceability and contain no sensitive data.
- Use repo-relative screenshot paths in any committed doc so later agents can open the evidence without absolute local paths.

The Compound Engineering output format used by the extensive path is documented in `references/compound-engineering-feedback-format.md`.

© EveryInc · MIT · EveryInc/compound-engineering-plugin

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor